Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add EricTechPro/startup-claude-skills --skill review-teamgit clone --depth 1 https://github.com/EricTechPro/startup-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team)<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-team/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-team"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.07421 |
| Opus 5.5 | $0.00019 | $0.02968 |
| Sonnet 5.5 | $0.00010 | $0.01484 |
| Haiku 4.5 | $0.00005 | $0.00742 |
Grade A, and why
review-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Team with Devil's Advocate
Orchestrate a team-based PR review using Agent Teams (TeamCreate + SendMessage). Four specialist reviewers analyze a GitHub PR, then a Devil's Advocate challenges every finding. Original reviewers must defend, adjust, or withdraw. Only surviving findings — with confidence ratings — appear in the final report.
When to Use This Skill
- Before merging a PR - Get high-confidence, adversarially filtered feedback
- For critical PRs - When false positives are costly (large features, infra changes)
- When you want fewer, better findings - Devil's Advocate filters noise
- For PRs with ticket context - Auto-detects ticket for acceptance criteria validation
Parameters
| Parameter | Default | Description |
|---|---|---|
| (first arg) | required | PR URL or PR number |
ticket |
auto-detect | Ticket key override (e.g., ticket=PROJ-94) |
skip-challenge |
false |
Skip Devil's Advocate phase (degrades to standard parallel review) |
verbose |
false |
Include full challenge/defense transcript in report |
Invocation
/review-team https://github.com/owner/repo/pull/123
/review-team 123
/review-team 123 ticket=PROJ-94
/review-team 123 skip-challenge=true
/review-team 123 verbose=true
Architecture
ORCHESTRATOR (main session - team lead, manages state + synthesis)
|
+-- Phase 0: INIT
| Parse PR URL, fetch metadata + diff, auto-detect ticket
| Read CLAUDE.md for project conventions
| TeamCreate("pr-review-{number}")
|
+-- Phase 1: TASK CREATION
| Create 5 tasks in shared task list (TaskCreate)
| Assign 4 reviewer tasks to specialist teammates
|
+-- Phase 2: PARALLEL REVIEW (4 agents work simultaneously)
| +-- staff-engineer (code-refactorer)
| +-- qa-engineer (general-purpose)
| +-- security-reviewer (general-purpose)
| +-- architect (system-architect)
| Each sends findings JSON to team lead via SendMessage
|
+-- Phase 3: DEVIL'S ADVOCATE CHALLENGE
| +-- devils-advocate (general-purpose)
| Receives ALL aggregated findings from Phase 2
| Sends targeted challenges to each original reviewer
|
+-- Phase 4: DEFENSE / REBUTTAL (4 agents respond)
| Each reviewer: DEFEND / ADJUST / WITHDRAW
| Sends responses to devils-advocate
|
+-- Phase 5: VERDICT
| devils-advocate assigns confidence ratings
| Sends final verdict to team lead
|
+-- Phase 6: SYNTHESIS
| Build unified report, shutdown teammates, TeamDelete
| Present report to user
|
+-- STATE: .review-team/state.json
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 840 lines · 48 tokens per session scan A 00caa59a4e81
review-team is a skill published in the GitHub repository EricTechPro/startup-claude-skills (60 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 7,421 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…